65 AI tools for Universal
picklesdev is an autonomous agent for end-to-end workflow automation, enabling users to run complete processes without manual intervention.
Let LlamaIndex agents run SignNow e-signature workflows via the SignNow MCP server.
A Python-to-Rust transpiler with semantic verification and memory safety analysis - compiles typed Python to a native binary via a single CLI command.
MCP server for MATLAB - run scripts/sections, inspect workspace variables, analyze figures, and lint code, with 15 tools.
npm supply-chain scanner catching obfuscated payloads, credential stealers, eBPF rootkits, and AI-key attacks that npm audit misses.
An MCP server that exposes any Python CLI app (Click, Typer, Argparse) as callable tools.
Team Relay MCP Server gives Claude Code, Codex, or OpenCode read/write access to a shared Obsidian vault, synced live.
OrigeneToolkit is a Python async context manager that provides an interface for interacting with Origene MCP server, with configurable timeout and automatic
Playwright MCPToolkit connects AI clients to browser automation via the Model Context Protocol, providing an interface to Playwright's automation library.
Spark MCP Server lets AI assistants search and retrieve AI assets from the Entire VC Spark catalog, hosted or run locally.
EdgeOnePagesMCPToolkit is an MCP server connector that provides an interface for interacting with EdgeOne Pages with optional timeout configuration.
A cookbook guide to building a GPT-5.1 coding agent with the Agents SDK that scaffolds, edits, and iterates on a codebase.
A promptfoo example for evaluating OpenAI's MCP tool integration, including auth and approval workflows.
A full promptfoo RAG example over SEC filings, with a PDF ingest pipeline and a Python retrieval provider.
Jupyter notebook demonstrating how to evaluate LLM answers about GitHub repositories using OpenAI Evals framework with custom datasets and MCP tools.
A promptfoo example demonstrating MCP provider configuration for evaluating Model Context Protocol servers through direct tool-calling tests, security checks
Simulate high error rates to test and validate retry functionality in AI prompt evaluation pipelines.
Promptfoo example for evaluating n8n AI agent workflows through a webhook-triggered provider.
A promptfoo example demonstrating custom API provider integration with CSV test cases for evaluating prompts against custom backends.
Archestra is an open-source enterprise AI platform unifying LLM and MCP gateways, agent runtime, RAG, and SSO/RBAC governance behind one URL.
A stateful Python execution environment that combines code, shell commands, and typed MCP tool calls in one local IPython kernel.
OneCite is a Python CLI and library that resolves DOIs, PMIDs, arXiv IDs, and other identifiers into clean, auditable BibTeX entries.
A security scanner for MCP servers that detects credential leaks, tool poisoning, prompt injection, and protocol-level attacks.
Prototype MCP agent that writes and runs TypeScript code composing MCP tools together, with progressive tool discovery and reusable skills.
An open-source MCP platform that runs any MCP server in an isolated container with identity, policy, and audit controls, on desktop or Kubernetes.
Rulebook generates AGENTS.md, quality gates, spec-driven tasks, and an MCP server for tool-agnostic AI coding agents.
Barkpark is a headless CMS for AI agents with a shared, real-time task board, Studio, CLI, TUI, and REST API.
SceneView is a multiplatform 3D and AR SDK for Android, iOS, Web, Desktop, Flutter, and React Native.
